scraper.py

import requests
from bs4 import BeautifulSoup
import pandas as pd

def get_stackoverflow_data(tag="linux-distribution", num_pages=3):
    base_url = "https://stackoverflow.com/questions/tagged/"
    data = []

    for page in range(1, num_pages + 1):
        url = f"{base_url}{tag}?tab=votes&page={page}"
        response = requests.get(url)

        if response.status_code == 200:
            soup = BeautifulSoup(response.content, "html.parser")
            questions = soup.find_all("div", class_="question-summary")

            for question in questions:
                title = question.find("h3").get_text().strip()
                vote_count = int(question.find("span", class_="vote-count-post").get_text())
                data.append({"title": title, "vote_count": vote_count})

    return data

if __name__ == "__main__":
    scraped_data = get_stackoverflow_data(tag="linux-distribution", num_pages=3)
    df = pd.DataFrame(scraped_data)
    df.to_csv("stack_overflow_data.csv", index=False)